INDEX

Explanations

code

oai_token-act-pair · gemini-2.0-flash

code symbols

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 beaver

-0.56

 wives

-0.53

 بيها

-0.51

 stork

-0.51

opra

-0.51

waukee

-0.50

 betweenstory

-0.50

ruptedException

-0.50

:✨

-0.49

ⓧ

-0.49

POSITIVE LOGITS

<bos>

0.66

 عنها

0.59

AutoScaleMode

0.56

InputLabel

0.56

 côtes

0.54

dataclass

0.53

GetResponse

0.53

freiheit

0.52

Cyfeiriadau

0.52

ZoneId

0.52

Activations Density 8.955%

code

code symbols

No Comments

No Known Activations